Research on Biomedical Engineering
Research on Biomedical Engineering
Original article

Prediction of 3D ground reaction forces during gait based on accelerometer data - Published Ahead of Print

Gustavo Leporace, Luiz Alberto Batista, Jurandir Nadal


Introduction: The aim of this study was to predict 3D ground reaction force signals based on accelerometer data during gait, using a feed-forward neural network (MLP). Methods: Seventeen healthy subjects were instructed to walk at a self-selected speed with a 3D accelerometer attached to the distal and anterior part of the shank. A force plate was embedded into the middle of the walkway. MLP neural networks with one hidden layer and three output layers were selected to simulate the anteroposterior (AP), vertical (Vert) and mediolateral (ML) ground reaction forces (GRF). The input layer was composed of fourteen inputs obtained from accelerometer signals, selected based on previous studies. Principal component analysis (PCA) was used to compare the simulated and collected curves. The Pearson correlation coefficient and the mean absolute deviation (MAD) between signals were calculated. Results: PCA identified small, but significant differences between collected and simulated signals in the loading response phases of AP and ML GRF, while Vert did not show differences. The correlation between the simulated and collected signals was high (AP: 0.97; Vert: 0.98; ML: 0.80). MAD was 1.8%BW for AP, 4.5%BW for Vert and 1.4%BW for ML. Conclusion: This study confirmed that multilayer perceptron neural network can predict the highly non-linear relationship of shank acceleration parameters and ground reaction forces, as well as other studies have done using plantar pressure devices. The greater advantages of this device are the low cost and the possibility of use outside the laboratory environment.


Acceleration, Force, Gait, Feedforward neural network, Simulation.


Baker R. Gait analysis methods in rehabilitation. J Neurol Rehabil. 2006; 2:3-4. PMid:16512912.

Barnett S, Cunningham JL, West S. A comparison of vertical force and temporal parameters produced by an in-shoe pressure measuring system and a force platform. Clin Biomech (Bristol, Avon). 2001; 16(4):353-7. PMid:11358623.

Chen JP, Chung MJ, Wu CY, Cheng KW, Wang MJ. Comparison of barefoot walking and shod walking between children with and without flat feet. J Am Podiatr Med Assoc. 2015; 105(3):218-25. PMid:26146967.

Cohen J. Statistical power analysis for the behavioral sciences. 2nd ed. New York: Lawrence Erlbaum Associates; 1988.

Elvin NG, Elvin AA, Arnoczky SP. Correlation between ground reaction force and tibial acceleration in vertical jumping. J Appl Biomech. 2007; 23(3):180-9. PMid:18089915.

Fasel B, Favre J, Chardonnens J, Gremion G, Aminian K. An inertial sensor-based system for spatio-temporal analysis in classic cross-country skiing diagonal technique. J Biomech. 2015; 48(12):3199-205. PMid:26209087.

Favre J, Aissaoui R, Jolles BM, de Guise JA, Aminian K. Functional calibration procedure for 3D knee joint angle description using inertial sensors. J Biomech. 2009; 42(14):2330-5. PMid:19665712.

Favre J, Hayoz M, Erhart-Hledik JC, Andriacchi TP. A neural network model to predict knee adduction moment during walking based on ground reaction force and anthropometric measurements. J Biomech. 2012; 45(4):692-8. PMid:22257888.

Fong DT, Chan YY, Hong Y, Yung PS, Fung KY, Chan KM. Estimating the complete ground reaction forces with pressure insoles in walking. J Biomech. 2008; 41(11):2597-601. PMid:18571656.

Forner-Cordero A, Koopman HJ, van der Helm FC. Use of pressure insoles to calculate the complete ground reaction forces. J Biomech. 2004; 37(9):1427-32. PMid:15275851.

Gruber AH, Boyer KA, Derrick TR, Hamill J. Impact shock frequency components and attenuation in rearfoot and forefoot running. J Sport Health Sci. 2014; 3(2):113-21.

Houck J, Kneiss J, Bukata SV, Puzas JE. Analysis of vertical ground reaction force variables during a Sit to Stand task in participants recovering from a hip fracture. Clin Biomech (Bristol, Avon). 2011; 26(5):470-6. PMid:21196069.

John CT, Seth A, Schwartz MH, Delp SL. Contributions of muscles to mediolateral ground reaction force over a range of walking speeds. J Biomech. 2012; 45(14):2438-43. PMid:22884038.

Jolliffe IT. Principal component analysis. New York: Springer-Verlag; 2002.

Jung Y, Jung M, Lee K, Koo S. Ground reaction force estimation using an insole-type pressure mat and joint kinematics during walking. J Biomech. 2014; 47(11):2693-9. PMid:24917473.

Leporace G, Batista LA, Metsavaht L, Nadal J. Residual analysis of ground reaction forces simulation during gait using neural networks with different configurations. In: Conference Proceedings of the IEEE Engineering and Medical Biology Society; Aug 25-29; Milan, Italy. USA: IEEE; 2015. p. 2812-15.

Leporace G, Batista LA, Muniz AM, Zeitoune G, Luciano T, Metsavaht L, Nadal J. Classification of gait kinematics of anterior cruciate ligament reconstructed subjects using principal component analysis and regressions modelling. In: Conference Proceedings of the IEEE Engineering and Medical Biology Society; 2012 Aug 28-Sept 1; San Diego, CA. USA: IEEE; 2012. p. 6514-7.

Lewis CL, Garibay EJ. Effect of increased pushoff during gait on hip joint forces. J Biomech. 2015; 48(1):181-5. PMid:25468661.

Liedtke C, Fokkenrood SA, Menger JT, van der Kooij H, Veltink PH. Evaluation of instrumented shoes for ambulatory assessment of ground reaction forces. Gait Posture. 2007; 26(1):39-47. PMid:17010612.

Liu Y, Shih SM, Tian SL, Zhong YJ, Li L. Lower extremity joint torque predicted by using artificial neural network during vertical jump. J Biomech. 2009; 42(7):906-11. PMid:19261287.

Muniz AM, Liu H, Lyons KE, Pahwa R, Liu W, Nobre FF, Nadal J. Comparison among probabilistic neural network, support vector machine and logistic regression for evaluating the effect of subthalamic stimulation in Parkinson disease on ground reaction force during gait. J Biomech. 2010; 43(4):720-6. PMid:19914622.

Oh SE, Choi A, Mun JH. Prediction of ground reaction forces during gait based on kinematics and a neural network model. J Biomech. 2013; 46(14):2372-80. PMid:23962528.

Orendurff MS, Schoen JA, Bernatz GC, Segal AD, Klute GK. How humans walk: bout duration, steps per bout, and rest duration. J Rehabil Res Dev. 2008; 45(7):1077-89. PMid:19165696.

Peruzzi A, Della Croce U, Cereatti A. Estimation of stride length in level walking using an inertial measurement unit attached to the foot: a validation of the zero velocity assumption during stance. J Biomech. 2011; 44(10):1991-4. PMid:21601860.

Rouhani H, Favre J, Crevoisier X, Aminian K. Ambulatory assessment of 3D ground reaction force using plantar pressure distribution. Gait Posture. 2010; 32(3):311-6. PMid:20576436.

Savelberg HHCM, Lange ALH. Assessment of the horizontal, fore-aft component of the ground reaction force from insole pressure patterns by using artificial neural networks. Clin Biomech (Bristol, Avon). 1999; 14(8):585-92. PMid:10521642.

Zadpoor AA, Nikooyan AA. The relationship between lower-extremity stress fractures and the ground reaction force: a systematic review. Clin Biomech (Bristol, Avon). 2011; 26(1):23-8. PMid:20846765.

5ba6ebc10e8825b77036c1ed rbejournal Articles
Links & Downloads

Res. Biomed. Eng.

Share this page
Page Sections